In this paper, we present an end-to-end language identification framework, the attention-based Convolutional Neural Network-Bidirectional Long-short Term Memory (CNN-BLSTM). The model is performed on the utterance level, which means the utterance-level decision can be directly obtained from the output of the neural network. To handle speech utterances with entire arbitrary and potentially long duration, we combine CNN-BLSTM model with a self-attentive pooling layer together. The front-end CNN-BLSTM module plays a role as local pattern extractor for the variable-length inputs, and the following self-attentive pooling layer is built on top to get the fixed-dimensional utterance-level representation. We conducted experiments on NIST LRE07 closed-set task, and the results reveal that the proposed attention-based CNN-BLSTM model achieves comparable error reduction with other state-of-the-art utterance-level neural network approaches for all 3 seconds, 10 seconds, 30 seconds duration tasks.
Utterance-level Permutation Invariant Training with Latency-controlled BLSTM for Single-channel Multi-talker Speech Separation
Tsinghua University（清华大学）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）；North China Power Engineering CO., LTD. of China Power Engineering Consulting Group（中国电力工程顾问集团华北电力设计院有限公司）
LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models
Samsung R\&D Institute India, Bangalore
近年来，基于深度学习的机器唇读已经变得突出。为此，已经提出了几种架构，如LipNet，LCANet等，与传统的唇读DNN-HMM混合系统相比，它们在DCT特征上训练的性能非常好。在这项工作中，我们提出了一种具有瓶颈层的3D-2D-CNN-BLSTM网络的更简单的架构。我们还提出了两种不同的唇读方法在这个架构的分析。在第一种方法中，3D-2D-CNN-BLSTM网络使用CTC字符损失（ch-CTC）进行训练。然后，在传统的ASR训练管道中，在瓶颈唇特征（从3D-2D-CNN-BLSTM ch-CTC网络中提取）上训练BLSTM-HMM模型。在第二种方法中，相同的3D-2D-CNN-BLSTM网络使用单词标签上的CTC损失（w-CTC）进行训练。第一种方法表明，瓶颈特征比DCT特征表现得更好。使用第二种方法在网格语料库的见人测试集上，我们报告了$1.3\%$ WER -一个相对于LCANet的$55\%$改进。在看不见的说话人测试集上，我们报告了$8.6\%$ WER，这是相对于LipNet的$24.5\%$改进。我们还验证了第二个数据集的$81$扬声器，我们收集的方法。最后，我们还讨论了特征重复对BLSTM-HMM模型性能的影响。
Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM
Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）；National Taiwan University（国立台湾大学）；Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所）
Insights into End-to-End Learning Scheme for Language Identification
Sun Yat-sen University（中山大学）；Duke Kunshan University（昆山杜克大学）；Carnegie Mellon University（卡内基梅隆大学）；Jiangsu Jinling Science and Technology Group Limited（江苏金陵科技集团有限公司）
Multi-stream Convolutional Neural Network with Frequency Selection for Robust Speaker Verification
Key Laboratory of Technology in Rural Water Management of Zhejiang Province（浙江省农村水利技术重点实验室）；College of Electric Engineering（电气工程学院）；Zhejiang University of Water Resources and Electric Power（水利与电力学院）
